INSPECTRE: Privately Estimating the Unseen
INSPECTRE: Privately Estimating the Unseen
复制标题
DOI：
10.29012/jpc.724
复制
发表时间：
2018-02
期刊：
影响因子：
--
通讯作者：
Jayadev Acharya;Gautam Kamath;Ziteng Sun;Huanyu Zhang
中科院分区：
文献类型：
--
作者：
Jayadev Acharya;Gautam Kamath;Ziteng Sun;Huanyu Zhang
我们开发了用于估计各种分布性质的不同的私有方法。给定来自离散分布p的样本、一些泛函f以及精度和隐私参数α和epsilon，目标是估计f(P)达到精度α，同时保持样本的epsilon-微分隐私。我们证明了这个问题对于几个感兴趣的泛函所需的样本大小几乎是紧界，包括支持度、支持覆盖率和熵。我们表明，在各种环境下，隐私的成本可以忽略不计，无论是理论上还是实验上都是如此。我们的方法是基于对几种估计这些性质的最新方法的敏感性分析，这些方法具有次线性样本复杂性
We develop differentially private methods for estimating various distributional properties. Given a sample from a discrete distribution p, some functional f, and accuracy and privacy parameters alpha and epsilon, the goal is to estimate f(p) up to accuracy alpha, while maintaining epsilon-differential privacy of the sample. We prove almost-tight bounds on the sample size required for this problem for several functionals of interest, including support size, support coverage, and entropy. We show that the cost of privacy is negligible in a variety of settings, both theoretically and experimentally. Our methods are based on a sensitivity analysis of several state-of-the-art methods for estimating these properties with sublinear sample complexities